© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 111924 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
111924

INDEX

Explanations

2

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_Widget

-0.07

 licenses

-0.07

 licensing

-0.06

 Kurds

-0.06

 platforms

-0.06

 bots

-0.06

 кирп

-0.06

 Heath

-0.06

es

-0.06

.didReceiveMemoryWarning

-0.06

POSITIVE LOGITS

0.09

_TM

0.08

、二

0.07

turtle

0.07

Two

0.07

Л

0.06

Some

0.06

٢

0.06

₂

0.06

呢

0.06

Activations Density 0.034%

No Known Activations